Added epubview from upstreamHEADmaster

8 files changed, 1066 insertions, 0 deletions

diff --git a/epubview/__init__.py b/epubview/__init__.py
new file mode 100644
index 0000000..81a3175
--- /dev/null
+++ b/epubview/__init__.py
@@ -0,0 +1,24 @@
+# Copyright 2009 One Laptop Per Child
+# Author: Sayamindu Dasgupta <sayamindu@laptop.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+import gobject
+
+gobject.threads_init()
+
+from epub import _Epub as Epub
+from epubview import _View as EpubView
+from jobs import _JobFind as JobFind
\ No newline at end of file
diff --git a/epubview/epub.py b/epubview/epub.py
new file mode 100644
index 0000000..81de9d7
--- /dev/null
+++ b/epubview/epub.py
@@ -0,0 +1,133 @@
+# Copyright 2009 One Laptop Per Child
+# Author: Sayamindu Dasgupta <sayamindu@laptop.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+import zipfile
+import tempfile
+import os, os.path
+from lxml import etree
+import shutil
+
+import navmap, epubinfo
+
+
+class _Epub(object):
+    def __init__(self, filepath):
+        self._filepath = filepath
+        self._zobject = None
+        self._obffile = None
+        self._obfpath = None
+        self._ncxpath = None
+        self._ncxfile = None
+        self._basepath = None
+        self._tempdir = tempfile.mkdtemp()
+        
+        if not self._verify():
+            print 'Warning: This does not seem to be a valid epub file'
+        
+        self._get_obf()
+        self._get_ncx()
+        
+        self._ncxfile = self._zobject.open(self._ncxpath)
+        self._navmap = navmap.NavMap(self._ncxfile, self._basepath)
+        
+        self._obffile = self._zobject.open(self._obfpath)
+        self._info = epubinfo.EpubInfo(self._obffile) 
+        
+        self._unzip()
+        
+    def _unzip(self):
+        #self._zobject.extractall(path = self._tempdir) # This is broken upto python 2.7
+        orig_cwd = os.getcwd()
+        os.chdir(self._tempdir)
+        for name in self._zobject.namelist():
+            if name.startswith(os.path.sep): # Some weird zip file entries start with a slash, and we don't want to write to the root directory
+                name = name[1:]
+            if name.endswith(os.path.sep) or name.endswith('\\'):
+                os.makedirs(name)
+            else:
+                self._zobject.extract(name)
+        os.chdir(orig_cwd)
+
+                
+    def _get_obf(self):
+        containerfile = self._zobject.open('META-INF/container.xml')
+        
+        tree = etree.parse(containerfile)
+        root = tree.getroot()
+        
+        for element in root.iterfind('.//{urn:oasis:names:tc:opendocument:xmlns:container}rootfile'):
+            if element.get('media-type') == 'application/oebps-package+xml':
+                self._obfpath = element.get('full-path')
+        
+        if self._obfpath.rpartition('/')[0]:        
+            self._basepath = self._obfpath.rpartition('/')[0] + '/'
+        else:
+            self._basepath = ''
+            
+        containerfile.close()
+
+
+    def _get_ncx(self):
+        obffile = self._zobject.open(self._obfpath)
+        
+        tree = etree.parse(obffile)
+        root = tree.getroot()
+
+        for element in root.iterfind('.//{http://www.idpf.org/2007/opf}item'):
+            if element.get('media-type') == 'application/x-dtbncx+xml' or \
+                element.get('id') == 'ncx':
+                self._ncxpath = self._basepath + element.get('href')
+        
+        obffile.close()
+        
+        
+    def _verify(self):
+        '''
+        Method to crudely check to verify that what we 
+        are dealing with is a epub file or not
+        '''
+        if not os.path.exists(self._filepath):
+            return False
+        
+        self._zobject = zipfile.ZipFile(self._filepath)
+        
+        if not 'mimetype' in self._zobject.namelist():
+            return False
+        
+        mtypefile = self._zobject.open('mimetype')
+        mimetype = mtypefile.readline()
+        
+        if mimetype != 'application/epub+zip':
+            return False
+        
+        return True
+    
+    def get_toc_model(self):
+        return self._navmap.get_gtktreestore()
+    
+    def get_flattoc(self):
+        return self._navmap.get_flattoc()
+    
+    def get_basedir(self):
+        return self._tempdir
+    
+    def get_info(self):
+        return self._info
+    
+    def close(self):
+        self._zobject.close()
+        shutil.rmtree(self._tempdir)
diff --git a/epubview/epubinfo.py b/epubview/epubinfo.py
new file mode 100644
index 0000000..ddf9ad5
--- /dev/null
+++ b/epubview/epubinfo.py
@@ -0,0 +1,90 @@
+import os
+from lxml import etree
+
+
+class EpubInfo(): #TODO: Cover the entire DC range
+    def __init__(self, file):
+        self._tree = etree.parse(file)
+        self._root = self._tree.getroot()
+        self._e_metadata = self._root.find('{http://www.idpf.org/2007/opf}metadata')
+        
+        self.title = self._get_title()
+        self.creator = self._get_creator()
+        self.date = self._get_date()
+        self.subject = self._get_subject()
+        self.source = self._get_source()
+        self.rights = self._get_rights()
+        self.identifier = self._get_identifier()
+        self.language = self._get_language()
+        
+    
+    def _get_data(self, tagname):
+        element = self._e_metadata.find(tagname)
+        return element.text
+    
+    def _get_title(self):
+        try:
+            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}title')
+        except AttributeError:
+            return None
+        
+        return ret
+        
+    def _get_creator(self):
+        try:
+            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}creator')
+        except AttributeError:
+            return None        
+        return ret
+        
+    def _get_date(self):
+        #TODO: iter
+        try:
+            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}date')
+        except AttributeError:
+            return None
+        
+        return ret
+
+    def _get_source(self):
+        try:
+            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}source')
+        except AttributeError:
+            return None
+        
+        return ret
+
+    def _get_rights(self):
+        try:
+            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}rights')
+        except AttributeError:
+            return None
+        
+        return ret
+
+    def _get_identifier(self):
+        #TODO: iter
+        element = self._e_metadata.find('.//{http://purl.org/dc/elements/1.1/}identifier')            
+
+        if element is not None:
+            return {'id':element.get('id'), 'value':element.text}
+        else:
+            return None
+
+    def _get_language(self):
+        try:
+            ret = self._get_data('.//{http://purl.org/dc/elements/1.1/}language')
+        except AttributeError:
+            return None
+        
+        return ret
+
+    def _get_subject(self):
+        try:
+            subjectlist = []
+            for element in self._e_metadata.iterfind('.//{http://purl.org/dc/elements/1.1/}subject'):
+                subjectlist.append(element.text)
+        except AttributeError:
+            return None
+        
+        return subjectlist
\ No newline at end of file
diff --git a/epubview/epubview.py b/epubview/epubview.py
new file mode 100644
index 0000000..f59fb9c
--- /dev/null
+++ b/epubview/epubview.py
@@ -0,0 +1,480 @@
+# Copyright 2009 One Laptop Per Child
+# Author: Sayamindu Dasgupta <sayamindu@laptop.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+import gtk, gtk.gdk
+import gobject
+import widgets
+
+import os.path
+import math
+import shutil
+
+from epub import _Epub
+from jobs import _JobPaginator as _Paginator
+
+
+LOADING_HTML = '''
+<div style="width:100%;height:100%;text-align:center;padding-top:50%;">
+    <h1>Loading...</h1>
+</div>
+'''
+
+class _View(gtk.HBox):
+    __gproperties__ = {
+        'has-selection' : (gobject.TYPE_BOOLEAN, 'whether has selection',
+                  'whether the widget has selection or not',
+                  0, gobject.PARAM_READABLE), 
+    'zoom' : (gobject.TYPE_FLOAT, 'the zoom level',
+                  'the zoom level of the widget',
+                  0.5, 4.0, 1.0, gobject.PARAM_READWRITE)
+    }    
+    __gsignals__ = {
+        'page-changed': (gobject.SIGNAL_RUN_FIRST,
+                          gobject.TYPE_NONE,
+                          ([]))
+    }    
+    def __init__(self):
+        gobject.threads_init()
+        gtk.HBox.__init__(self)
+        
+        self.connect("destroy", self._destroy_cb)
+
+        self._ready = False
+        self._paginator = None
+        self._loaded_page = -1
+        #self._old_scrollval = -1
+        self._loaded_filename = None
+        self._pagecount = -1
+        self.__going_fwd = True
+        self.__going_back = False
+        self.__page_changed = False
+        self.has_selection = False
+        self.zoom = 1.0
+        self._epub = None
+        self._findjob = None
+        self.__in_search = False
+        self.__search_fwd = True
+        
+        self._sw = gtk.ScrolledWindow()
+        self._view = widgets._WebView()
+        self._view.load_string(LOADING_HTML, 'text/html', 'utf-8', '/')
+        settings = self._view.get_settings()
+        settings.props.default_font_family = 'DejaVu LGC Serif'
+        settings.props.enable_plugins = False
+        settings.props.default_encoding = 'utf-8'
+        self._view.connect('load-finished', self._view_load_finished_cb)
+        self._view.connect('scroll-event', self._view_scroll_event_cb)
+        self._view.connect('key-press-event', self._view_keypress_event_cb)
+        self._view.connect('button-release-event', self._view_buttonrelease_event_cb)
+        self._view.connect('selection-changed', self._view_selection_changed_cb)
+        self._view.connect_after('populate-popup', self._view_populate_popup_cb)
+        
+        self._sw.add(self._view)
+        self._sw.set_policy(gtk.POLICY_AUTOMATIC, gtk.POLICY_NEVER)
+        self._v_vscrollbar = self._sw.get_vscrollbar()
+        self._v_scrollbar_value_changed_cb_id = self._v_vscrollbar.connect('value-changed', \
+                                                                        self._v_scrollbar_value_changed_cb)
+        self._scrollbar = gtk.VScrollbar()
+        self._scrollbar.set_update_policy(gtk.UPDATE_DISCONTINUOUS)
+        self._scrollbar_change_value_cb_id = self._scrollbar.connect('change-value', \
+                                                                      self._scrollbar_change_value_cb)
+        self.pack_start(self._sw, expand = True, fill = True)
+        self.pack_start(self._scrollbar, expand = False, fill = False)
+        
+        self._view.set_flags(gtk.CAN_DEFAULT|gtk.CAN_FOCUS)        
+        
+    def set_document(self, epubdocumentinstance):
+        self._epub = epubdocumentinstance
+        gobject.idle_add(self._paginate)
+
+    def do_get_property(self, property):
+        if property.name == 'has-selection':
+            return self.has_selection
+        elif property.name == 'zoom':
+            return self.zoom
+        else:
+            raise AttributeError, 'unknown property %s' % property.name
+
+    def do_set_property(self, property, value):
+        if property.name == 'zoom':
+            self.__set_zoom(value)
+        else:
+            raise AttributeError, 'unknown property %s' % property.name
+    
+    def get_has_selection(self):
+        return self.get_property('has-selection')
+    
+    def get_zoom(self):
+        return self.get_property('zoom')
+    
+    def set_zoom(self, value):
+        self.set_property('zoom', value)
+    
+    def zoom_in(self):
+        if self.can_zoom_in():
+            self.set_zoom(self.get_zoom() + 0.1)
+            return True
+        else:
+            return False
+
+    def zoom_out(self):
+        if self.can_zoom_out():
+            self.set_zoom(self.get_zoom() - 0.1)
+            return True
+        else:
+            return False
+    
+    def can_zoom_in(self):
+        if self.zoom < 4:
+            return True
+        else:
+            return False
+
+    def can_zoom_out(self):
+        if self.zoom > 0.5:
+            return True
+        else:
+            return False
+    
+    def get_current_page(self):
+        return self._loaded_page
+    
+    def get_current_file(self):
+        #return self._loaded_filename
+        if self._paginator: 
+            return self._paginator.get_file_for_pageno(self._loaded_page)
+        else:
+            return None
+    
+    def get_pagecount(self):
+        return self._pagecount
+    
+    def set_current_page(self, n):
+        if n < 1 or n > self._pagecount:
+            return False
+        self._load_page(n)
+        return True
+        
+    def next_page(self):
+        if self._loaded_page == self._pagecount:
+            return False
+        self._load_next_page()
+        return True
+        
+    def previous_page(self):
+        if self._loaded_page == 1:
+            return False
+        self._load_prev_page()
+        return True
+
+    def scroll(self, scrolltype, horizontal):
+        if scrolltype == gtk.SCROLL_PAGE_BACKWARD:
+            self.__going_back = True
+            self.__going_fwd = False
+            if not self._do_page_transition():
+                self._view.move_cursor(gtk.MOVEMENT_PAGES, -1)
+        elif scrolltype == gtk.SCROLL_PAGE_FORWARD:
+            self.__going_back = False
+            self.__going_fwd = True
+            if not self._do_page_transition():
+                self._view.move_cursor(gtk.MOVEMENT_PAGES, 1)
+        else:
+            print ('Got unsupported scrolltype %s' % str(scrolltype))
+    
+    def copy(self):
+        self._view.copy_clipboard()
+    
+    def find_next(self):
+        self._view.grab_focus()
+        self._view.grab_default()
+
+        if self._view.search_text(self._findjob.get_search_text(), \
+                               self._findjob.get_case_sensitive(), True, False):
+            return
+        else:
+            path = os.path.join(self._epub.get_basedir(), self._findjob.get_next_file())
+            self.__in_search = True
+            self.__search_fwd = True
+            self._load_file(path)
+    
+    def find_previous(self):
+        self._view.grab_focus()
+        self._view.grab_default()
+
+        if self._view.search_text(self._findjob.get_search_text(), \
+                               self._findjob.get_case_sensitive(), False, False):
+            return
+        else:
+            path = os.path.join(self._epub.get_basedir(), self._findjob.get_prev_file())
+            self.__in_search = True
+            self.__search_fwd = False
+            self._load_file(path)
+
+    def _find_changed(self, job):
+        self._view.grab_focus()
+        self._view.grab_default()
+        self._findjob = job
+        #self._view.search_text(self._findjob.get_search_text(), \
+        #                       self._findjob.get_case_sensitive(), True, False)
+        self.find_next()
+        
+    def __set_zoom(self, value):
+        self._view.set_zoom_level(value)
+        self.zoom = value
+    
+    def __set_has_selection(self, value):
+        if value != self.has_selection:
+            self.has_selection = value
+            self.notify('has-selection')
+    
+    def _view_populate_popup_cb(self, view, menu):
+        menu.destroy() #HACK
+        return
+    
+    def _view_selection_changed_cb(self, view):
+        # FIXME: This does not seem to be implemented in 
+        # webkitgtk yet
+        print view.has_selection()
+    
+    def _view_buttonrelease_event_cb(self, view, event):
+        # Ugly hack
+        self.__set_has_selection(view.can_copy_clipboard() \
+                                 | view.can_cut_clipboard())
+    
+    def _view_keypress_event_cb(self, view, event):
+        name = gtk.gdk.keyval_name(event.keyval)
+        if name == 'Page_Down' or name == 'Down': 
+            self.__going_back = False
+            self.__going_fwd = True
+        elif name == 'Page_Up' or name == 'Up':
+            self.__going_back = True
+            self.__going_fwd = False
+            
+        self._do_page_transition()
+
+    def _view_scroll_event_cb(self, view, event):
+        if event.direction == gtk.gdk.SCROLL_DOWN:
+            self.__going_back = False
+            self.__going_fwd = True
+        elif event.direction == gtk.gdk.SCROLL_UP:
+            self.__going_back = True
+            self.__going_fwd = False
+
+        self._do_page_transition() 
+    
+    def _do_page_transition(self):
+        if self.__going_fwd:
+            if self._v_vscrollbar.get_value() >= \
+                self._v_vscrollbar.props.adjustment.props.upper - \
+                    self._v_vscrollbar.props.adjustment.props.page_size:
+                self._load_next_file()
+                return True
+        elif self.__going_back:
+            if self._v_vscrollbar.get_value() == self._v_vscrollbar.props.adjustment.props.lower:
+                self._load_prev_file()
+                return True
+        
+        return False
+        
+    def _view_load_finished_cb(self, v, frame):
+        filename = self._view.props.uri.replace('file://', '')
+        if os.path.exists(filename.replace('xhtml', 'xml')):
+            filename = filename.replace('xhtml', 'xml') # Hack for making javascript work
+        
+        if self._loaded_page < 1 or filename == None:
+            return False
+        
+        self._loaded_filename = filename
+        
+        remfactor = self._paginator.get_remfactor_for_file(filename)
+        pages = self._paginator.get_pagecount_for_file(filename)
+        extra = int(math.ceil(remfactor * self._view.get_page_height()/(pages-remfactor)))
+        if extra > 0:
+            self._view.add_bottom_padding(extra)
+        
+        if self.__in_search:
+            self._view.search_text(self._findjob.get_search_text(), \
+                               self._findjob.get_case_sensitive(), \
+                               self.__search_fwd, False)
+            self.__in_search = False
+        else:
+            if self.__going_back:
+                # We need to scroll to the last page
+                self._scroll_page_end()
+            else:
+                self._scroll_page()
+
+    def _scroll_page_end(self):
+        v_upper = self._v_vscrollbar.props.adjustment.props.upper
+        v_page_size = self._v_vscrollbar.props.adjustment.props.page_size
+        self._v_vscrollbar.set_value(v_upper)
+        
+    def _scroll_page(self):
+        pageno = self._loaded_page
+        
+        v_upper = self._v_vscrollbar.props.adjustment.props.upper
+        v_page_size = self._v_vscrollbar.props.adjustment.props.page_size
+        
+        scrollfactor = self._paginator.get_scrollfactor_pos_for_pageno(pageno)
+        self._v_vscrollbar.set_value((v_upper - v_page_size) * scrollfactor)
+        
+    def _paginate(self):
+        filelist = []
+        for i in self._epub._navmap.get_flattoc():
+            filelist.append(os.path.join(self._epub._tempdir, i[1]))
+            
+        self._paginator = _Paginator(filelist)
+        self._paginator.connect('paginated', self._paginated_cb)
+    
+    def _load_next_page(self):
+        self._load_page(self._loaded_page + 1)
+
+    def _load_prev_page(self):
+        self._load_page(self._loaded_page - 1)
+    
+    def _v_scrollbar_value_changed_cb(self, scrollbar):
+        if self._loaded_page < 1:
+            return
+        scrollval = scrollbar.get_value()
+        scroll_upper = self._v_vscrollbar.props.adjustment.props.upper
+        scroll_page_size = self._v_vscrollbar.props.adjustment.props.page_size
+
+        if self.__going_fwd == True and not self._loaded_page == self._pagecount:
+            if self._paginator.get_file_for_pageno(self._loaded_page) != \
+                self._paginator.get_file_for_pageno(self._loaded_page + 1):
+                return # We don't need this if the next page is in another file
+
+            scrollfactor_next = self._paginator.get_scrollfactor_pos_for_pageno(self._loaded_page + 1)
+            if scrollval > 0:
+                scrollfactor = scrollval/(scroll_upper - scroll_page_size)
+            else:
+                scrollfactor = 0
+            if scrollfactor >= scrollfactor_next:
+                self._on_page_changed(self._loaded_page + 1)
+        elif self.__going_back == True and self._loaded_page > 1:
+            if self._paginator.get_file_for_pageno(self._loaded_page) != \
+                        self._paginator.get_file_for_pageno(self._loaded_page - 1):
+                return
+
+            scrollfactor_cur = self._paginator.get_scrollfactor_pos_for_pageno(self._loaded_page)
+            if scrollval > 0:
+                scrollfactor = scrollval/(scroll_upper - scroll_page_size)
+            else:
+                scrollfactor = 0
+
+            if scrollfactor <= scrollfactor_cur:
+                self._on_page_changed(self._loaded_page - 1)
+        
+    def _on_page_changed(self, pageno):
+        self.__page_changed = True
+        self._loaded_page = pageno
+        self._scrollbar.handler_block(self._scrollbar_change_value_cb_id)
+        self._scrollbar.set_value(pageno)
+        self._scrollbar.handler_unblock(self._scrollbar_change_value_cb_id)
+        self.emit('page-changed')
+        
+    def _load_page(self, pageno):
+        if pageno > self._pagecount or pageno < 1:
+            #TODO: Cause an exception
+            return
+
+        self._on_page_changed(pageno)
+        filename = self._paginator.get_file_for_pageno(pageno)
+        if filename != self._loaded_filename:
+            #self._loaded_filename = filename
+            if filename.endswith('xml'):
+                dest = filename.replace('xml', 'xhtml')
+                shutil.copy(filename.replace('file://', ''), dest.replace('file://', ''))
+                self._view.open(dest)
+            else:
+                self._view.open(filename)
+        else:
+            self._scroll_page()
+    
+    def _load_next_file(self):
+        cur_file = self._paginator.get_file_for_pageno(self._loaded_page)
+        pageno = self._loaded_page
+        while pageno < self._paginator.get_total_pagecount():
+            pageno += 1
+            if self._paginator.get_file_for_pageno(pageno) != cur_file:
+                break
+        
+        self._load_page(pageno)
+
+    def _load_file(self, path):
+        #TODO: This is a bit suboptimal - fix it
+        for pageno in range(1, self.get_pagecount()):
+            filepath = self._paginator.get_file_for_pageno(pageno)
+            if filepath.endswith(path):
+                self._load_page(pageno)
+                break
+
+    def _load_prev_file(self):
+        cur_file = self._paginator.get_file_for_pageno(self._loaded_page)
+        pageno = self._loaded_page
+        while pageno > 1:
+            pageno -= 1
+            if self._paginator.get_file_for_pageno(pageno) != cur_file:
+                break
+            
+        self._load_page(pageno)
+
+    def _scrollbar_change_value_cb(self, range, scrolltype, value):
+        if scrolltype == gtk.SCROLL_STEP_FORWARD:
+            self.__going_fwd = True
+            self.__going_back = False
+            if not self._do_page_transition():
+                self._view.move_cursor(gtk.MOVEMENT_DISPLAY_LINES, 1)
+        elif scrolltype == gtk.SCROLL_STEP_BACKWARD:
+            self.__going_fwd = False
+            self.__going_back = True
+            if not self._do_page_transition():
+                self._view.move_cursor(gtk.MOVEMENT_DISPLAY_LINES, -1)                
+        elif scrolltype == gtk.SCROLL_JUMP or \
+            scrolltype == gtk.SCROLL_PAGE_FORWARD or \
+                scrolltype == gtk.SCROLL_PAGE_BACKWARD:
+            if value > self._scrollbar.props.adjustment.props.upper:
+                self._load_page(self._pagecount)
+            else:
+                self._load_page(round(value))
+        else:
+            print 'Warning: unknown scrolltype %s with value %f' % (str(scrolltype), value)
+        
+        self._scrollbar.set_value(self._loaded_page) #FIXME: This should not be needed here
+        
+        if self.__page_changed == True:
+            self.__page_changed = False
+            return False
+        else:
+            return True
+        
+    def _paginated_cb(self, object):
+        self._ready = True
+        
+        self._pagecount = self._paginator.get_total_pagecount()
+        self._scrollbar.set_range(1.0, self._pagecount - 1.0)
+        self._scrollbar.set_increments(1.0, 1.0)
+        self._view.grab_focus()
+        self._view.grab_default()
+        if self._loaded_page < 1:
+            self._load_page(1)
+        
+        
+
+    def _destroy_cb(self, widget):
+        self._epub.close()
+
diff --git a/epubview/jobs.py b/epubview/jobs.py
new file mode 100644
index 0000000..de276b3
--- /dev/null
+++ b/epubview/jobs.py
@@ -0,0 +1,248 @@
+# Copyright 2009 One Laptop Per Child
+# Author: Sayamindu Dasgupta <sayamindu@laptop.org>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, write to the Free Software
+# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+
+
+import gobject
+import gtk
+import widgets
+import cairo
+
+import math
+import os.path
+import BeautifulSoup
+
+import epub
+
+import threading
+
+PAGE_WIDTH = 135
+PAGE_HEIGHT = 216
+
+def _pixel_to_mm(pixel, dpi):
+    inches = pixel/dpi
+    return int(inches/0.03937)
+
+def _mm_to_pixel(mm, dpi):
+    inches = mm * 0.03937
+    return int(inches * dpi)
+
+
+
+class SearchThread(threading.Thread):
+    def __init__(self, obj):
+        threading.Thread.__init__ (self)
+        self.obj = obj
+        self.stopthread = threading.Event()
+
+    def _start_search(self):
+        for entry in self.obj.flattoc:
+            if self.stopthread.isSet():
+                break
+            name, file = entry
+            filepath = os.path.join(self.obj._document.get_basedir(), file)
+            f = open(filepath)
+            if self._searchfile(f):
+                self.obj._matchfilelist.append(file)
+            f.close()
+        
+        gtk.gdk.threads_enter()
+        self.obj._finished = True 
+        self.obj.emit('updated')
+        gtk.gdk.threads_leave()
+        
+        return False
+    
+    def _searchfile(self, fileobj):
+        soup = BeautifulSoup.BeautifulSoup(fileobj)
+        body = soup.find('body')
+        tags = body.findChildren(True)
+        for tag in tags:
+            if not tag.string is None: 
+                if tag.string.find(self.obj._text) > -1:
+                    return True
+    
+        return False
+
+    def run (self):
+        self._start_search()
+      
+    def stop(self):
+        self.stopthread.set()
+
+
+
+class _JobPaginator(gobject.GObject):
+    __gsignals__ = {
+        'paginated': (gobject.SIGNAL_RUN_FIRST,
+                          gobject.TYPE_NONE,
+                          ([]))
+    }   
+    def __init__(self, filelist):
+        gobject.GObject.__init__(self)
+        
+        self._filelist = filelist
+        self._filedict = {}
+        self._pagemap = {}
+        
+        self._bookheight = 0
+        self._count = 0
+        self._pagecount = 0
+        
+        self._screen = gtk.gdk.screen_get_default()
+        self._old_fontoptions = self._screen.get_font_options()
+        options = cairo.FontOptions()
+        options.set_hint_style(cairo.HINT_STYLE_MEDIUM)
+        options.set_antialias(cairo.ANTIALIAS_GRAY)
+        options.set_subpixel_order(cairo.SUBPIXEL_ORDER_DEFAULT)
+        options.set_hint_metrics(cairo.HINT_METRICS_DEFAULT)
+        self._screen.set_font_options(options)
+        
+        self._temp_win = gtk.Window()
+        self._temp_view = widgets._WebView()
+
+        settings = self._temp_view.get_settings()
+        settings.props.default_font_family = 'DejaVu LGC Serif'
+        settings.props.sans_serif_font_family = 'DejaVu LGC Sans'
+        settings.props.serif_font_family = 'DejaVu LGC Serif'
+        settings.props.monospace_font_family = 'DejaVu LGC Sans Mono'
+        settings.props.enforce_96_dpi = True
+        #settings.props.auto_shrink_images = False #FIXME: This does not seem to work
+        settings.props.enable_plugins = False
+        settings.props.default_font_size = 12
+        settings.props.default_monospace_font_size = 10
+        settings.props.default_encoding = 'utf-8'
+        
+        sw = gtk.ScrolledWindow()
+        sw.set_policy(gtk.POLICY_NEVER, gtk.POLICY_NEVER)
+        self._dpi = 96
+        sw.set_size_request(_mm_to_pixel(PAGE_WIDTH, self._dpi), _mm_to_pixel(PAGE_HEIGHT, self._dpi))
+        sw.add(self._temp_view)
+        self._temp_win.add(sw)
+        self._temp_view.connect('load-finished', self._page_load_finished_cb)
+           
+        self._temp_win.show_all()
+        self._temp_win.unrealize()
+        
+        self._temp_view.open(self._filelist[self._count])
+       
+    def _page_load_finished_cb(self, v, frame):
+        f = v.get_main_frame()
+        pageheight = v.get_page_height()
+                
+        if pageheight <= _mm_to_pixel(PAGE_HEIGHT, self._dpi):
+            pages = 1
+        else:
+            pages = pageheight/float(_mm_to_pixel(PAGE_HEIGHT, self._dpi))
+        for i in range(1, int(math.ceil(pages) + 1)):
+            if pages - i < 0:
+                pagelen = (pages - math.floor(pages))/pages
+            else:
+                pagelen = 1/pages
+            self._pagemap[float(self._pagecount + i)] = (f.props.uri, (i-1)/math.ceil(pages), pagelen)
+        
+        self._pagecount += math.ceil(pages)
+        self._filedict[f.props.uri.replace('file://', '')] = (math.ceil(pages), math.ceil(pages) - pages)
+        self._bookheight += pageheight
+        
+        if self._count+1 >= len(self._filelist):
+            self._temp_win.destroy()
+            self._screen.set_font_options(self._old_fontoptions)
+            self.emit('paginated')
+        else:
+            self._count += 1
+            self._temp_view.open(self._filelist[self._count])
+            
+            
+    def get_file_for_pageno(self, pageno):
+        return self._pagemap[pageno][0]
+    
+    def get_scrollfactor_pos_for_pageno(self, pageno):
+        return self._pagemap[pageno][1]
+
+    def get_scrollfactor_len_for_pageno(self, pageno):
+        return self._pagemap[pageno][2]
+    
+    def get_pagecount_for_file(self, file):
+        return self._filedict[file][0]
+
+    def get_remfactor_for_file(self, file):
+        return self._filedict[file][1]
+    
+    def get_total_pagecount(self):
+        return self._pagecount
+
+    def get_total_height(self):
+        return self._bookheight
+
+
+class _JobFind(gobject.GObject):
+    __gsignals__ = {
+        'updated': (gobject.SIGNAL_RUN_FIRST,
+                          gobject.TYPE_NONE,
+                          ([]))
+    }
+    def __init__(self, document, start_page, n_pages, text, case_sensitive=False):
+        gobject.GObject.__init__(self)
+        gtk.threads_init()
+        
+        self._finished = False
+        self._document = document
+        self._start_page = start_page
+        self._n_pages = n_pages
+        self._text = text
+        self._case_sensitive = case_sensitive
+        self.flattoc = self._document.get_flattoc()
+        self._matchfilelist = []
+        self._current_file_index = 0
+        self.threads = []
+        
+        s_thread = SearchThread(self)
+        self.threads.append(s_thread)
+        s_thread.start()
+        
+    def cancel(self):
+        for s_thread in self.threads:
+            s_thread.stop()
+    
+    def is_finished(self):
+        return self._finished
+    
+    def get_next_file(self):
+        self._current_file_index += 1
+        try:
+            path = self._matchfilelist[self._current_file_index]
+        except IndexError:
+            self._current_file_index = 0
+            path = self._matchfilelist[self._current_file_index]
+   
+        return path
+
+    def get_prev_file(self):
+        self._current_file_index -= 1
+        try:
+            path = self._matchfilelist[self._current_file_index]
+        except IndexError:
+            self._current_file_index = -1
+            path = self._matchfilelist[self._current_file_index]
+   
+        return path
+
+    def get_search_text(self):
+        return self._text
+    
+    def get_case_sensitive(self):
+        return self._case_sensitive
diff --git a/epubview/modules/webkit.so b/epubview/modules/webkit.so
new file mode 100755
index 0000000..f8dce2a
--- /dev/null
+++ b/epubview/modules/webkit.so
diff --git a/epubview/navmap.py b/epubview/navmap.py
new file mode 100644
index 0000000..0ba0b8f
--- /dev/null
+++ b/epubview/navmap.py
@@ -0,0 +1,64 @@
+from lxml import etree
+import gtk
+
+class NavPoint(object):
+    def __init__(self, label, contentsrc, children = []):
+        self._label = label
+        self._contentsrc = contentsrc
+        self._children = children 
+        
+    def get_label(self):
+        return self._label
+    
+    def get_contentsrc(self):
+        return self._contentsrc
+    
+    def get_children(self):
+        return self._children
+
+
+class NavMap(object):
+    def __init__(self, file, basepath):
+        self._basepath = basepath
+        self._tree = etree.parse(file)
+        self._root = self._tree.getroot()
+        self._gtktreestore = gtk.TreeStore(str, str)
+        self._flattoc = []
+        
+        self._populate_toc()
+ 
+    def _populate_toc(self):
+        navmap = self._root.find('{http://www.daisy.org/z3986/2005/ncx/}navMap')       
+        for navpoint in navmap.iterfind('./{http://www.daisy.org/z3986/2005/ncx/}navPoint'):
+            self._process_navpoint(navpoint)
+            
+    def _gettitle(self, navpoint):
+        text = navpoint.find('./{http://www.daisy.org/z3986/2005/ncx/}navLabel/{http://www.daisy.org/z3986/2005/ncx/}text')
+        return text.text
+
+    def _getcontent(self, navpoint):
+        text = navpoint.find('./{http://www.daisy.org/z3986/2005/ncx/}content/')
+        return self._basepath + text.get('src')
+
+    def _process_navpoint(self, navpoint, parent = None):
+        title = self._gettitle(navpoint)
+        content = self._getcontent(navpoint)
+        
+        iter = self._gtktreestore.append(parent, [title, content])
+        self._flattoc.append((title, content))
+        
+        childnavpointlist = list(navpoint.iterfind('./{http://www.daisy.org/z3986/2005/ncx/}navPoint'))
+        
+        if len(childnavpointlist):
+            for childnavpoint in childnavpointlist:
+                self._process_navpoint(childnavpoint, parent = iter)   
+        else: 
+            return
+             
+    def get_gtktreestore(self):
+        return self._gtktreestore
+    
+    def get_flattoc(self):
+        return self._flattoc
+    
+#t = TocParser('/home/sayamindu/Desktop/Test/OPS/fb.ncx')
\ No newline at end of file
diff --git a/epubview/widgets.py b/epubview/widgets.py
new file mode 100644
index 0000000..19d2dc9
--- /dev/null
+++ b/epubview/widgets.py
@@ -0,0 +1,27 @@
+try:
+    import webkit
+except ImportError:
+    import os, sys
+    sys.path.append(os.path.join(os.environ['SUGAR_BUNDLE_PATH'], 'epubview', 'modules'))
+    import webkit
+
+import gtk
+
+
+class _WebView(webkit.WebView):
+    def __init__(self):
+        webkit.WebView.__init__(self)
+        
+    def get_page_height(self):
+        #TODO: Need to check status of page load
+        js = 'oldtitle=document.title;document.title=document.body.clientHeight;'
+        self.execute_script(js)
+        ret = self.get_main_frame().get_title()
+        js = 'document.title=oldtitle;'
+        self.execute_script(js)
+        return int(ret)
+        
+    def add_bottom_padding(self, incr):
+        js = ('var newdiv = document.createElement("div");newdiv.style.height = "%dpx";document.body.appendChild(newdiv);' % incr)
+        self.execute_script(js)
+